© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98631
    Prev
    Next
    INDEX
    Explanations

    aged or ago

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens and digit sequences (e.g. years, dates, quantities).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     that
    -1.80
     primarily
    -1.54
     like
    -1.48
     because
    -1.48
     usually
    -1.38
     several
    -1.34
    ?
    -1.32
     many
    -1.30
     more
    -1.30
     frequently
    -1.28
    POSITIVE LOGITS
    Ꮗ
    1.50
    (!__
    1.42
     provincie
    1.38
    くれました
    1.36
    艄
    1.34
     hadde
    1.30
    꿩
    1.27
     atan
    1.27
    Ύ
    1.26
    Упаковка
    1.25
    Activations Density 0.084%

    No Known Activations